Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12064
    Prev
    Next
    INDEX
    Explanations

    HTML tag elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML markup, especially the head section and resource-loading tags/attributes in code snippets.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.66
    tagHelperRunner
    -0.63
    SharedCtor
    -0.63
    AutoScaleMode
    -0.60
    lamy
    -0.58
    InSection
    -0.57
     becauſe
    -0.57
     <>",
    -0.56
    Życiorys
    -0.55
    Witam
    -0.55
    POSITIVE LOGITS
    link
    0.90
    meta
    0.83
     link
    0.73
     חיצוניים
    0.66
     meta
    0.64
    LINK
    0.59
    UrlResolution
    0.58
    title
    0.54
    STYLE
    0.54
     linkage
    0.54
    Activations Density 0.147%

    No Known Activations